lkml.org 
[lkml]   [2012]   [Sep]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Out of memory on 3.5 kernels
Good morning,

Dave Kleikamp [Tue, Sep 25, 2012 at 10:07:14AM -0500]:
> >> Active / Total Objects (% used) : 1165130 / 1198087 (97.2%)
> >> Active / Total Slabs (% used) : 81027 / 81027 (100.0%)
> >> Active / Total Caches (% used) : 69 / 101 (68.3%)
> >> Active / Total Size (% used) : 1237249.81K / 1246521.94K (99.3%)
> >> Minimum / Average / Maximum Object : 0.01K / 1.04K / 15.23K
> >>
> >> OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
> >> 993607 993607 100% 1.21K 75358 26 2411456K jfs_ip
> >
> > Well that doesn't look good. 100% of the inode cache for jfs are being
> > used which either means
> >
> > - there's a memory leak, or
>
> maybe a missing iput() somewhere?
>
> Nico, does unmounting the usb drive after killing the backup clean up
> the jfs inode cache?

Iirc, it does not. I'll check this evening, because doing the backup
currently forces me to reboot my productive system.

> > - there's some sort of throttling issue in jfs.
> >
> > And those objects are consuming ~2.3GB of slab on your 4GB machine and
> > seems to only have occurred between v3.4.2 to v3.5.3.
>
> Almost nothing in jfs has changed between these releases. Only this:
>
> vfs: Rename end_writeback() to clear_inode()

The other obscurity is that the root filesystem is also jfs - it's not
only the usb disk.

Cheers,

Nico

--
PGP key: 7ED9 F7D3 6B10 81D7 0EC5 5C09 D7DC C8E4 3187 7DF0


\
 
 \ /
  Last update: 2012-09-26 10:21    [W:0.107 / U:1.128 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site